Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade
Monitoring the state of wind turbine blades in real-time using sensors is crucial for early fault diagnosis. Several studies have been conducted to predict the failure of wind turbine blades based on data measured by sensors. These methods rely on accuracy of the sensor-monitoring data; even minor a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9938966/ |
| _version_ | 1828290581752709120 |
|---|---|
| author | Wai-Xi Liu Rui-Peng Yin Ping-Yu Zhu |
| author_facet | Wai-Xi Liu Rui-Peng Yin Ping-Yu Zhu |
| author_sort | Wai-Xi Liu |
| collection | DOAJ |
| description | Monitoring the state of wind turbine blades in real-time using sensors is crucial for early fault diagnosis. Several studies have been conducted to predict the failure of wind turbine blades based on data measured by sensors. These methods rely on accuracy of the sensor-monitoring data; even minor abnormalities can lead to misjudgment of the blade condition and cause serious consequences in service. Nevertheless, self-diagnosing schemes for sensor faults are less researched. The data measured by all sensors on the same wind turbine blade constitutes a spatiotemporal joint distribution dataset, which forms a data correlation pattern. Therefore, this paper proposes a sensor fault self-diagnosing scheme that does not depend on any labeled fault data. First, a sensor data prediction model based on deep learning is built by mining the inherent relevance between sensors. Second, a sensor fault is detected when the residual between the measured sensor value and the predicted value exceeds the control limit. The experimental results for a real-world wind turbine blade show that the model has good prediction and fault diagnosis performance. |
| first_indexed | 2024-04-13T10:36:50Z |
| format | Article |
| id | doaj.art-49eb444d6be74cbdbee7eaed59476377 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T10:36:50Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-49eb444d6be74cbdbee7eaed594763772022-12-22T02:50:01ZengIEEEIEEE Access2169-35362022-01-011011722511723410.1109/ACCESS.2022.32194809938966Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine BladeWai-Xi Liu0https://orcid.org/0000-0002-7343-4948Rui-Peng Yin1Ping-Yu Zhu2School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou, ChinaSchool of Mechanical and Electric Engineering, Guangzhou University, Guangzhou, ChinaMonitoring the state of wind turbine blades in real-time using sensors is crucial for early fault diagnosis. Several studies have been conducted to predict the failure of wind turbine blades based on data measured by sensors. These methods rely on accuracy of the sensor-monitoring data; even minor abnormalities can lead to misjudgment of the blade condition and cause serious consequences in service. Nevertheless, self-diagnosing schemes for sensor faults are less researched. The data measured by all sensors on the same wind turbine blade constitutes a spatiotemporal joint distribution dataset, which forms a data correlation pattern. Therefore, this paper proposes a sensor fault self-diagnosing scheme that does not depend on any labeled fault data. First, a sensor data prediction model based on deep learning is built by mining the inherent relevance between sensors. Second, a sensor fault is detected when the residual between the measured sensor value and the predicted value exceeds the control limit. The experimental results for a real-world wind turbine blade show that the model has good prediction and fault diagnosis performance.https://ieeexplore.ieee.org/document/9938966/Deep learningfault diagnosispredictionspatiotemporalwind turbine |
| spellingShingle | Wai-Xi Liu Rui-Peng Yin Ping-Yu Zhu Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade IEEE Access Deep learning fault diagnosis prediction spatiotemporal wind turbine |
| title | Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade |
| title_full | Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade |
| title_fullStr | Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade |
| title_full_unstemmed | Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade |
| title_short | Deep Learning Approach for Sensor Data Prediction and Sensor Fault Diagnosis in Wind Turbine Blade |
| title_sort | deep learning approach for sensor data prediction and sensor fault diagnosis in wind turbine blade |
| topic | Deep learning fault diagnosis prediction spatiotemporal wind turbine |
| url | https://ieeexplore.ieee.org/document/9938966/ |
| work_keys_str_mv | AT waixiliu deeplearningapproachforsensordatapredictionandsensorfaultdiagnosisinwindturbineblade AT ruipengyin deeplearningapproachforsensordatapredictionandsensorfaultdiagnosisinwindturbineblade AT pingyuzhu deeplearningapproachforsensordatapredictionandsensorfaultdiagnosisinwindturbineblade |